Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{174300,
        author = {Kush Pandya and Gaurav Kulkarni and Vrunda Patel and Abbas Eralwala},
        title = {Deep Learning Approaches for Financial Sentiment Prediction: Leveraging LSTM and Transformer Models},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {3370-3375},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174300},
        abstract = {The financial market is profoundly influenced by the sentiments expressed in news articles, economic reports, and financial analyses. Sentiment analysis of financial news provides critical insights for investors and traders, helping them anticipate market fluctuations and make informed decisions. Traditional methods for sentiment analysis often struggle with the complexity of financial language, which contains subtle nuances and context- dependent interpretations. To address these challenges, this re- search develops and implements a neural network based on long- short-term memory (LSTM) to classify the sentiment of financial news articles as positive or negative. The approach involves rigorous data preprocessing, model training, evaluation, and web deployment. The study achieves a training accuracy of 74.96%, demonstrating the potential of deep learning models to capture complex textual patterns. Although the model faced challenges with the accuracy of the validation, it provides a foundational approach for future advancements in financial sentiment analysis.},
        keywords = {Sentiment Analysis, LSTM, Financial Markets, Deep Learning, Natural Language Processing},
        month = {March},
        }